AUV Navigation Research Articles

Integration of Deep Sequence Learning-Based Virtual GPS Model and EKF for AUV Navigation

Integration of Deep Sequence Learning-Based Virtual GPS Model and EKF for AUV Navigation

A Joint Graph-Based Approach for Simultaneous Underwater Localization and Mapping for AUV Navigation Fusing Bathymetric and Magnetic-Beacon-Observation Data

A Joint Graph-Based Approach for Simultaneous Underwater Localization and Mapping for AUV Navigation Fusing Bathymetric and Magnetic-Beacon-Observation Data

A Low-Cost and High-Precision Underwater Integrated Navigation System

The traditional underwater integrated navigation system is based on an optical fiber gyroscope and Doppler Velocity Log, which is high-precision but also expensive, heavy, bulky and difficult to adapt to the development requirements of AUV swarm, intelligence and miniaturization. This paper proposes a low-cost, light-weight, small-volume and low-computation underwater integrated navigation system based on MEMS IMU/DVL/USBL. First, according to the motion formula of AUV, a five-dimensional state equation of the system was established, whose dimension was far less than that of the traditional. Second, the main source of error was considered. As the velocity observation value of the system, the velocity measured by DVL eliminated the scale error and lever arm error. As the position observation value of the system, the position measured by USBL eliminated the lever arm error. Third, to solve the issue of inconsistent observation frequencies between DVL and USBL, a sequential filter was proposed to update the extended Kalman filter. Finally, through selecting the sensor equipment and conducting two lake experiments with total voyages of 5.02 km and 3.2 km, respectively, the correctness and practicality of the system were confirmed by the results. By comparing the output of the integrated navigation system and the data of RTK GPS, the average position error was 4.12 m, the maximum position error was 8.53 m, the average velocity error was 0.027 m/s and the average yaw error was 1.41°, whose precision is as high as that of an optical fiber gyroscope and Doppler Velocity Log integrated navigation system, but the price is less than half of that. The experimental results show that the proposed underwater integrated navigation system could realize the high-precision and long-term navigation of AUV in the designated area, which had great potential for both military and civilian applications.

Terrain-Aided Navigation of Long-Range AUV Based on Cubature Particle Filter

Terrain-Aided Navigation of Long-Range AUV Based on Cubature Particle Filter

An outlier-robust Rao–Blackwellized particle filter for underwater terrain-aided navigation

Terrain-aided navigation (TAN) is one of the key techniques for autonomous navigation and positioning of AUVs. This paper develops a novel integrated navigation system that combines the inertial navigation system (INS) and TAN into one filter, in contrast to the conventional INS/TAN model. This method not only provides a position estimate for the carrier but also the INS error, which increases the filtering dimension significantly. Thus, the Rao-Blackwellized particle filter (RBPF) technique is introduced to address the “dimensional disaster” problem. A three-dimensional (3-D) model is established to estimate the horizontal position while compensating for the tidal inaccuracy by extending the tidal depth bias to the state space. Furthermore, the variable and complex underwater environment can potentially result in outlier interference in depth measurements, which significantly degrades the performance of the RBPF-based estimation algorithm. This paper thus presents a 3-D adaptive RBPF method based on the maximum correntropy criterion (MCC) to suppress the influence of measurement outliers on positioning precision. Simulations and experimental tests verify the effectiveness of the proposed algorithm. The results demonstrated that the 3-D model-based AMCCRBPF method can effectively improve robustness to outliers and provide an accurate estimate of the tidal depth bias.

Improved Adaptive Finch Clustering Sonar Segmentation Algorithm Based on Data Distribution and Posterior Probability

This study proposes a side-scan sonar target detection technique for CPU or low-performance GPU to meet the requirement of underwater target detection. To rectify the gray distribution of the original side scan sonar data, enhance picture segmentation, and supply the data distribution probability for the clustering algorithm, the methodology uses a classic image processing technique that is GPU-friendly. The modified adaptive Finch clustering technique is used to segment the image and remove image voids after assessing the processed image attributes. The posterior information is then used to apply a classification label to each pixel. The characteristics of the connected region are analyzed in the data playback of the Tuandao experiment in accordance with the imaging principle of side-scan sonar and the original shape and size characteristics of the target. The predicted target results are combined with the AUV navigation information to obtain the predicted target longitude and latitude information, which is then sent to the AUV master control system to guide the next plan. The Jiaozhou Bay sea test results demonstrate that the traditional target detection algorithm put forth in this paper can be integrated into a low-performance GPU to detect targets and locate them. The detection accuracy and speed exhibit strong performance, and real-time autonomous sonar detection is made possible.

Sequential learning navigation method and general correction model for Autonomous Underwater Vehicle

The errors introduced in the modeling and state estimation by conventional navigation methods will affect the AUV navigation accuracy. Therefore, this paper proposes a sequential learning method for AUV navigation. Firstly, a Temporal Convolutional Network (TCN) module is used to learn the temporal relationships from raw sensor data. After the feature representation, a Self-Attention (SA) mechanism is implemented to weigh the data at different time steps. Finally, the Fully Connected (FC) layers are adopted to regress the AUV displacements. Since the sequential learning navigation method does not require state estimation computation and can calculate the AUV position by displacement accumulation, it can avoid introducing related errors. Meanwhile, this paper proposes a general correction model based on the sequential learning method to correct the errors of various state estimation techniques. The experimental results based on actual sea trial data from Sailfish 210 AUV show that the average AUV navigation accuracy of the presented sequential learning method is improved by 56.78% compared to EKF, 57.64% compared to UKF, and 47.85% compared to CKF. Meanwhile, the navigation accuracy of the proposed general correction model is improved by 62.88% compared to EKF, 49.45% compared to UKF, and 42.86% compared to CKF.

Underwater Navigation of AUVs Using Uncorrelated Measurement Error Model of USBL

<i>This article presents a modeling method for the uncorrelated measurement error of the ultra-short baseline (USBL) acoustic positioning system for aiding navigation of underwater vehicles. The Mahalanobis distance (MD) and principal component analysis are applied to decorrelate the errors of USBL measurements, which are correlated in the x- and y-directions and vary according to the relative direction and distance between a reference station and the underwater vehicles. The proposed method can decouple the radial-direction error and angular direction error from each USBL measurement, where the former and latter are independent and dependent, respectively, of the distance between the reference station and the vehicle. With the decorrelation of the USBL errors along the trajectory of the vehicles in every time step, the proposed method can reduce the threshold of the outlier decision level. To demonstrate the effectiveness of the proposed method, simulation studies were performed with motion data obtained from a field experiment involving an autonomous underwater vehicle and USBL signals generated numerically by matching the specifications of a specific USBL with the data of a global positioning system. The simulations indicated that the navigation system is more robust in rejecting outliers of the USBL measurements than conventional ones. In addition, it was shown that the erroneous estimation of the navigation system after a long USBL blackout can converge to the true states using the MD of the USBL measurements. The navigation systems using the uncorrelated error model of the USBL, therefore, can effectively eliminate USBL outliers without loss of uncontaminated signals.</i>

Sliding Mode Motion Control for AUV with Dual-Observer Considering Thruster Uncertainty

In the motion control of AUVs, especially those driven by multiple thrusters, the thruster misalignment and thrust loss cause the actual force and moment applied to the AUV to deviate from that desired, making accurate and fast motion control difficult. This paper proposes a sliding mode control method with dual-observer estimation for the AUV 3D motion control problem in the presence of thruster misalignment uncertainty and thrust loss uncertainty. Firstly, this paper considers the force and moment deviation as disturbances that vary with the controller output, and proposes the TD disturbance observer to address the problem of deviation caused by uncertainty in thruster misalignment. Secondly, this paper introduces the dynamics equation of thrust loss and designs the gain disturbance observer to estimate the thrust loss uncertainty during AUV navigation. The designed controller, verified by simulation and field tests, ensures that the AUV maintains better motion control despite thruster misalignment and thrust loss.

AUV Navigation Correction Based on Automated Multibeam Tile Matching.

Ocean science and hydroacoustic seafloor mapping rely on accurate navigation underwater. By exploiting terrain information provided by a multibeam echosounder system, it is possible to significantly improve map quality. This article presents an algorithm capable of improving map quality and accuracy by aligning consecutive pings to tiles that are matched pairwise. A globally consistent solution is calculated from these matches. The proposed method has the potential to be used online in addition to other navigation solutions, but is mainly targeted for post processing. The algorithm was tested using different parameter settings on an AUV and a ship-based dataset. The ship-based dataset is publicly available as a benchmark. The original accurate navigation serving as a ground truth, alongside trajectories that include an artificial drift, are available. This allows quantitative comparisons between algorithms and parameter settings.

Stereo-vision-based AUV navigation system for resetting the inertial navigation system error

Stereo-vision-based AUV navigation system for resetting the inertial navigation system error

Dual closed loop AUV trajectory tracking control based on finite time and state observer.

The three-dimensional trajectory tracking of AUV is an important basis for it to complete its task. Due to many uncertain disturbances such as wind, wave and current on the sea, it is easy to cause problems such as slow convergence speed of the controller and saturation of the controller output in the three-dimensional trajectory tracking control of AUV. And the dynamic uncertainty of AUV's own model will have a great negative impact on AUV's trajectory tracking control. In order to solve the problem of slow convergence speed of the above controller, the finite time control method is introduced into the designed position controller. In order to solve the problem of AUV controller output saturation, an auxiliary dynamic system is designed to compensate the system control output saturation. In order to solve the uncertainty of AUV model, a reduced order extended observer is designed in the dynamic controller. It can observe the motion parameters of AUV at any time, and compensate the uncertainty of model uncertainty and external environment disturbance in real time. The control method in this paper is simulated in a three-dimensional model. The experimental results show that the convergence speed, control accuracy, robustness and tracking effect of AUV are higher than those of common trajectory tracker. The algorithm is loaded into the "sea exploration Ⅱ" AUV and verified by experiments in Suzhou lake. The effect of AUV navigation basically meets the task requirements, in which the mean value of pitch angle and heading angle error is less than 8 degrees and the mean value of depth error is less than 0.1M. The trajectory tracker can better meet the trajectory tracking control needs of the AUV.

AUV Dynamic Obstacle Avoidance Method Based on Improved PPO Algorithm

A reasonable obstacle avoidance method for AUV 3D path planning is difficult. Existing obstacle avoidance methods have certain drawbacks. For example, they are only applicable to 2D planar applications and cannot effectively handle dynamic obstacles. To address these problems, this study designs an obstacle collision prediction model (CPM). Based on the results of the simulation operation of the obstacle inertial motion, the safety of the AUV navigation is evaluated to improve the sensitivity of the model to dynamic obstacles. Then, the learning ability of the sequence sample data is enhanced by combining it with the long short-term memory (LSTM) network, and the training efficiency and effect of the algorithm are improved. The trained proximal policy optimization (PPO) network can output reasonable actions to control the AUV to avoid obstacles, forming an AUV 3D dynamic obstacle avoidance strategy based on CPM-LSTM-PPO algorithm. The simulation results show that the proposed algorithm has good generalization in uncertain environments, and successfully realizes dynamic obstacle avoidance of AUV in different three-dimensional unknown environments, providing theoretical and technical support for real path planning.

Human pose estimation and LSTM-based diver heading prediction for AUV navigation guidance

Human pose estimation and LSTM-based diver heading prediction for AUV navigation guidance

Position Correction Model Based on Gated Hybrid RNN for AUV Navigation

Underwater autonomous navigation technology is a key link for AUV to complete various underwater missions successfully. In this paper, we have proposed a position correction model based on hybrid gated RNN, which does not need to establish a motion model like typical navigation algorithms, to avoid modeling errors in the navigation process. According to the low update rate of GPS and the slip data caused by the coverage of GPS antenna during the process of floating and diving, it does not meet the actual requirements of navigation and control. We proposed to use improved EKF and iSAM as the output of the training dataset to filter out GPS slips, then the position error is corrected at the same time. First, the normalized input sequence is fed to the two-layer hybrid gated RNN with BiLSTM output mode as sequence and LSTM output mode as last, and then the processed data is fed to the two fully connected layers with a dropout layer added in the middle. After that, the output of the position correction model can be obtained through the regression layer. To confirm the validity of the proposed model, we conducted sea trials to compare the proposed model with EKF and iSAM. The experimental results prove that the proposed position correction model performs better than EKF and iSAM in all aspects, and the correction model trained with iSAM is more effective than that trained with EKF.

Real-time in situ prediction of ocean currents

The prediction of ocean currents is essential for the path planning and control of Autonomous Underwater Vehicles. Regional physics-based forecast models provide valid predictions but are too computationally expensive for real-time prediction necessary for AUV navigation. While vehicle sensors can measure the spatial evolution of currents, temporal prediction remains an open problem as existing data-driven models with real-time capabilities have only been shown to work at locations where data have been used to develop the model. We propose in this paper two predictive tools using deep learning techniques, a Long Short-Term Memory (LSTM) Recurrent Neural Network and a Transformer, to perform real-time in-situ prediction of ocean currents at any location. A data set from the National Oceanic and Atmospheric Administration is split in two distinct sets to train and test the models. We show that the LSTM and the Transformer have an averaged Normalized Root Mean Squared Error respectively of 0.10 and 0.11 over all test sites with a standard deviation respectively of 0.024 and 0.031. Comparisons with Harmonic Method predictions at various locations in the territorial sea of the United States show that both models provide state-of-the-art accuracy without having been trained with data from these sites.

Cooperative single-beacon multiple AUV navigation under stringent communication bandwidth constraints

In this paper we propose a method of cooperative navigation of a fleet of AUVs moving in formation with stringent limitations on the bandwidth of the underlying acoustic communications network. In the methodology proposed, one vehicle is equipped with a DVL and the others are equipped with acoustic modems and range-measuring devices that can only measure ranges to the remaining vehicles in the formation and to an underwater beacon or transponder located at a known position. Based on DVL and range measurements, and through the exchange of information among the vehicles, each vehicle must estimate its own position and the positions of the other vehicles in the fleet. The estimates obtained are then used for geo-referencing purposes as well as formation control. We use methods of distributed and quantised state estimation to solve this problem. We investigate through numerical simulations what type of information should be shared among the vehicles (range measurements or position estimates) for an efficient tradeoff between bandwidth and state estimation performance, which may lead to a better scalability of the formation.

Navigation and guidance control system of UNUSAITS AUV based on dynamical system using ensemble kalman filter square root

This study presents the development of navigation system of AUV. It is initially in the form of a nonlinear system model to determine the trajectory for the AUV motion control. The non-linear system model of UNUSAITS AUV is then implemented in the Square Root Ensemble Kalman filter (SR-EnKF) to estimate the trajectory of the AUV. The developed EnKF algorithm covers two types of simulations. The contribution from this paper is trajectory or position estimation of nonlinear UNUSAITS AUV system with 6-DOF AUV model. The result of model estimation is presented based on numeric study and simulation. The first simulation is dedicated to generate 400 ensembles, and the second simulation is to generate 400 ensembles. The second simulation shows that the 500 ensembles give more accurate results. A further examination on the accuracy has been performed by accounting for the RMSE of actual condition and the estimation from the simulation, which yields the range of accuracy between 97 % up to 99%.

Improved Navigation and Guidance System of AUV Using Sensors Fusion

Improved Navigation and Guidance System of AUV Using Sensors Fusion

Observing the Oceans Acoustically

Acoustics play a central role in mankind’s interactions with the ocean and the life within. Passive listening to ocean “soundscapes” informs us about the physical and bio-acoustic environment from earthquakes to communication between fish. Active acoustic probing of the environment informs us about ocean topography, currents and temperature, and abundance and type of marine life vital to fisheries and biodiversity related interests. The two together in a multi-purpose network can lead to discovery and improve understanding of ocean ecosystem health and biodiversity, climate variability and change, and marine hazards and maritime safety. Passive acoustic monitoring (PAM) of sound generated and utilized by marine life as well as other natural (wind, rain, ice, seismics) and anthropogenic (shipping, surveys) sources, has dramatically increased worldwide to enhance understanding of ecological processes. Characterizing ocean soundscapes (the levels and frequency of sound over time and space, and the sources contributing to the sound field), temporal trends in ocean sound at different frequencies, distribution and abundance of marine species that vocalize, and distribution and amount of human activities that generate sound in the sea, all require passive acoustic systems. Acoustic receivers are now routinely acquiring data on a global scale, e.g., Comprehensive Nuclear-Test-Ban Treaty Organization International Monitoring System hydroacoustic arrays, various regional integrated ocean observing systems, and some profiling floats. Judiciously-placed low-frequency acoustic sources transmitting to globally distributed PAM and other systems provide: 1) high temporal resolution measurements of large-scale ocean temperature/heat content variability, taking advantage of the inherent integrating nature of acoustic travel-time data using tomography; and 2) acoustic positioning (“underwater GPS”) and communication services enabling basin-scale undersea navigation and management of floats, gliders, and AUVs. This will be especially valuable in polar regions with ice cover. Routine deployment of sources during repeat global-scale hydrographic ship surveys would provide high spatial coverage snapshots of ocean temperatures. To fully exploit the PAM systems, precise timing and positioning need to be broadly implemented. Ocean sound is now a mature Global Ocean Observing System (GOOS) “essential ocean variable”, which is one crucial step toward providing a fully integrated global multi-purpose ocean acoustic observing system.